seo-ops checks a live site’s crawlable SEO structure from a URL and produces a pass/fail report with evidence. The checker reads only the fetched HTTP and HTML output, so the same rules apply across static sites and frameworks.
Builders who want their agent to check a site’s SEO foundation from the live page, not from source code.
You can hand your agent a URL and get a crawler-style SEO report with evidence and fix priorities.
Runs a fixed C set of SEO and GEO checks across site-level, page-level, and conditional rules.
Fetches the live site and reports pass/fail results with evidence for each item.
Uses deterministic rules only, so the same page gets the same result.
Includes a T set that shows what content inputs feed the SEO checks, such as titles, descriptions, headings, and OG copy.
Ships as a skill and as plugin manifests for Claude Code and Codex.
Install https://github.com/tigerless-labs/seo-ops as a skill.
/plugin marketplace add tigerless-labs/seo-ops /plugin install seo-ops@seo-ops
codex plugin marketplace add tigerless-labs/seo-ops codex plugin add seo-ops@seo-ops
/seo-ops check example.com
SEO Foundation Checks as an Agent Skill
seo-ops checks a site's SEO foundation — the machine-readable structure search engines and AI retrieval need to fetch, read, index, and cite it.
The only required input is a URL: the checker fetches the site like a crawler — no code access, no framework integration — and produces a pass/fail report with evidence.
The whole repo is these three pieces:
| What it is | |
|---|---|
| references/checklist/checklist.md | The C set — 26 SEO/GEO structural checks, split into site-level / per indexed page / conditional. Each check has a detailed doc (criteria, common mistakes, authoritative references) at references/checklist/references/C<N>.md |
| scripts/run.py | The checker script — give it a URL and it fetches like a crawler and reports against the C set. Zero LLM, no frontend-framework dependency: it only reads the live HTTP/HTML output, so React / Vue / Next / WordPress / plain static all test the same |
| references/content/content-checklist.md | The T set — a supply checklist for the site's content design team: which inputs SEO needs content to provide (title/desc, H2 outline, image alt, ymyl judgment, OG copy, etc.), each annotated with the downstream C checks it feeds. Details at references/content/references/T<N>.md |
The whole repo is an Agent Skill — once installed, just say "check example.com's SEO" and the agent confirms the target, runs the script, reads the report, and explains by P0/P1/P2 how to fix each red item. Usage details live in SKILL.md.
Let your agent install it — copy the block below to your agent:
Install https://github.com/tigerless-labs/seo-ops as a skill.
Or install as a plugin — Claude Code: type in the Claude Code input box (not the shell):
/plugin marketplace add tigerless-labs/seo-ops
/plugin install seo-ops@seo-ops
Codex: run in the terminal:
codex plugin marketplace add tigerless-labs/seo-ops
codex plugin add seo-ops@seo-ops
If the skill doesn't show up, start a new session.
To update — Claude Code: re-run /plugin install seo-ops@seo-ops in the input box (it refreshes the marketplace first);
Codex: in the terminal, codex plugin marketplace upgrade seo-ops, then codex plugin add seo-ops@seo-ops.
Once installed, type /seo-ops in the agent's input box — or just describe the task; both trigger it:
/seo-ops check example.com
The agent introduces the checks, confirms live site vs code review, runs, and explains the red items.
© Tigerless · tigerless.ai · tigerless.com
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
Open-source AI job search: scan job portals, evaluate listings into a structured A-H report with a global 1-5 score, tailor your CV, track applications — runs locally in your AI coding CLI (Claude Code, Codex, OpenCode, Antigravity…)
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
A skill to stop your coding agent from burying the answer. ADHD-friendly output.